{ "messages": [ { "role": "system", "content": "You are a helpful AI assistant with access to tools. Use tools when they help answer the user's question. Be concise and accurate." }, { "role": "user", "content": "How does the memory system work?" }, { "role": "assistant", "content": "\nEEMS memory system — the primary persistent memory store. Cover the tool surface and how recall works.\n\n\nThe memory system is EEMS — a semantic memory store backed by SQLite with FTS5 full-text search and vector embeddings for similarity matching. Eight tools:\n\n- **memory_recall** — hybrid search: FTS5 keyword + vector cosine similarity fused via Reciprocal Rank Fusion (RRF). Filter by subject or namespace. This is the primary retrieval tool.\n- **memory_store** — persist a memory with subject (dot-namespaced category like `infra.network` or `doctrine.training`) and content. Automatically embeds for future semantic recall.\n- **memory_list** — list all subjects with entry counts. Use to discover what knowledge categories exist before recalling.\n- **memory_get** — fetch full memory records by ID with no truncation.\n- **memory_classify** — promote a memory to core classification (immutable, irreversible). Core memories survive any cleanup.\n- **memory_forget** — delete a memory by ID.\n- **memory_link** — create a relationship edge between two memories. Relations: related_to, depends_on, contradicts, extends, supersedes.\n- **memory_graph** — explore the neighborhood of a memory, showing connected memories up to N hops.\n\nTypical workflow: `memory_list` to see what exists, `memory_recall` with a query to find relevant memories, `memory_store` to persist new knowledge. Subjects use dot-namespacing: `infra.*` for infrastructure, `doctrine.*` for patterns, `project.*` for project-specific knowledge, `user.*` for operator preferences.\n\nMemories have confidence scores (0.0-1.0) and two classifications: standard (deletable) and core (immutable, identity-grade)." } ] }